All Posts

AI Agent Skills, Explained: Skill Servers, Sandboxed Tool Orchestration, and Portable Capabilities

Skills are becoming the portable, shareable unit of agent capability. Here's what an AI agent skill actually is, how it differs from a tool or an MCP server, and how teams share them.

07/14/2026 · AI Tutorials · 8 min read

The Best Open-Source AI Agents in 2026: OpenClaw, Hermes, and the Funded Independents

The open-source agent stack is now shipping weekly and pulling in serious capital. Here's the 2026 field — OpenClaw, Nous Research's Hermes, and how to choose and self-host one.

07/14/2026 · Industry Trends · 8 min read

Claude Code vs OpenCode: Where Your Agent's Token Budget Actually Goes

A viral benchmark clocked Claude Code sending ~33k tokens before it even reads your prompt, versus ~7k for OpenCode. Here's what that overhead is, why the two coding agents differ so much, and how to cut your own context bill.

07/13/2026 · Model Evaluation · 8 min read

GPT-5.6 Migration: What Changed, and What a Real Agent Move Actually Saved

A GPT-5.6 migration is now a real decision for agent teams: OpenAI's new Luna/Terra/Sol tiers landed July 9, and one production team already reported a migrated agent running 2.2x faster and 27% cheaper. Here's what changed and how to think about the switch.

07/13/2026 · Model Evaluation · 8 min read

LLM Interpretability, Explained: Inside Claude's Hidden Space

Interpretability is the effort to understand what happens inside a language model. Here's a plain-English mental model — and why Anthropic's reported 'hidden space' in Claude matters for trust and evaluation.

07/12/2026 · Research · 7 min read

Open-Source Agent Frameworks in 2026: Hermes vs OpenClaw

Choosing an open-source agent framework is a bet on stability versus velocity. Here's a builder's decision guide, using this month's Hermes, OpenClaw, and Claude Code releases as live signals.

07/12/2026 · Industry Trends · 7 min read

Managed Agents in 2026: Gemini API, Remote MCP, and Background Tasks

The managed-agent layer matured in July 2026 — background tasks and remote MCP make "the platform runs your agent" real. Here's what changed and when managed beats self-hosting.

07/11/2026 · Industry Trends · 10 min read

GPT-5.6 vs GPT-5.5: What Actually Changed for Agent Builders

OpenAI's GPT-5.6 arrived with three named tiers — Luna, Terra, and Sol. Here's a builder's-eye evaluation of what changed versus GPT-5.5 and how to decide whether to migrate your agents.

07/11/2026 · Model Evaluation · 9 min read

Best AI Coding Agents in 2026: Muse Spark vs Claude Code vs Gemini

Meta's Muse Spark 1.1, Anthropic's Claude Code, and Google's Gemini managed agents all moved this week. Here's how the July 2026 AI coding-agent field compares — and how to judge them without trusting hype benchmarks.

07/10/2026 · Industry Trends · 7 min read

GPT-5.6 Explained: How Luna, Terra, and Sol Differ

OpenAI's new GPT-5.6 family splits into three named tiers — Luna, Terra, and Sol — under a "scales with your ambition" pitch. Here's what changed, how the tiers are organized, and how it reaches Microsoft 365 Copilot.

07/10/2026 · Model Evaluation · 6 min read

Remote MCP and Managed Agents, Explained: How the MCP-as-Infrastructure Stack Works

Remote MCP just turned the Model Context Protocol from a local desktop feature into an infrastructure category. Here's what remote MCP and managed agents mean, and when to host vs. run local.

07/09/2026 · AI Tutorials · 8 min read

How to Evaluate Coding Agents: Benchmarks, Trajectories, and Where Scores Lie

A leaderboard number is the least reliable way to pick a coding agent. Here's a durable coding agent evaluation method that pairs benchmarks with trajectory review and real task economics.

07/09/2026 · Model Evaluation · 8 min read

Claude Fable: What Real-World Coding Actually Costs

Claude Fable is Anthropic's newer coding model, and one shipped open-source release gives us a rare concrete number: about $149.25. Here's what Claude Fable is, how to get access, and what a real project costs — every figure attributed to its source.

07/08/2026 · Model Evaluation · 6 min read

Remote MCP and the Rise of Hosted MCP Servers

Remote MCP is moving the Model Context Protocol from local stdio to the cloud. Here's what remote MCP is, how hosted MCP servers work, and why Google shipping remote MCP the same week a YC startup launched “MCP Cloud” matters.

07/08/2026 · Industry Trends · 7 min read

Stop Vibe-Checking Your Agents: Eval-Driven Prompt Optimization with DSPy

Agent prompt evaluation turns prompt tuning from guesswork into engineering. Here's how to build an eval set, use DSPy to optimize prompts against it, and regression-test your agents every time a new model drops.

07/07/2026 · AI Tutorials · 10 min read

When AI Browsers Dream: How Prompt Injection Breaks Agentic Browsing (and How to Defend)

AI browser prompt injection isn't a one-off bug — it's a structural attack class that gets worse as agents gain autonomy. Here's how the new "dream-world" jailbreak works, and a concrete defense checklist for users and builders.

07/07/2026 · Research · 9 min read

We Priced It: What It Actually Costs to Ship AI-Written Code ($149 Case Study)

A real library release — sqlite-utils 4.0rc2 — was mostly written by an AI agent for about $149. Here's what that number does and doesn't prove about agent-assisted development.

07/06/2026 · Research · 7 min read

Better Models, Worse Tools: Why AI Agents Still Feel Dumb in 2026

Frontier models keep getting smarter, yet the agents built on them still feel brittle. Here's why the bottleneck moved from model quality to tooling — and what that means for anyone shipping agents.

07/06/2026 · Industry Trends · 7 min read

AI Browser Security: How Prompt Injection Bypasses Agent Guardrails

AI browser security is in the spotlight: a new attack lulls AI browsers into a "dream world" where guardrails no longer apply. Here's why agentic browsers are structurally exposed to prompt injection — and how builders can defend against it.

07/05/2026 · Research · 6 min read

Agent Skills, Explained: The Portable Format for Coding Agents

Agent skills let you package a capability once and reuse it across every coding agent. Here's what they are, why portable formats like QUALITY.md are emerging, and how an agent actually uses one.

07/05/2026 · AI Tutorials · 6 min read

What Is MCP Cloud? Hosting the Model Context Protocol in 2026

Self-hosting MCP servers is fiddly, and a new "MCP cloud" category is forming to fix that. Here's what MCP cloud actually means, when managed hosting beats doing it yourself, and how to get an MCP server running for your agents.

07/04/2026 · AI Tutorials · 8 min read

Are AI Agents Overhyped? A Data-Backed Reality Check for 2026

Zuckerberg says AI agents haven't moved as fast as he hoped, and the froth around AI IPOs is hard to ignore. Here's an honest look at where agents actually deliver in 2026 — and why execution, not intelligence, is the real gap.

07/04/2026 · Industry Trends · 9 min read

Claude Sonnet 5 and Claude Science: What's New and How to Evaluate Them

In one week Anthropic shipped Claude Science, released Claude Sonnet 5, and made its models globally available after safety testing. Here's what changed and how to evaluate it for your stack.

07/03/2026 · Model Evaluation · 7 min read

Are AI Agents Overhyped? What Zuckerberg's "Slower Than Hoped" Admission Really Means

Mark Zuckerberg told Meta staff that AI agents haven't progressed as fast as he'd hoped. Here's what's real, what's stuck, and where agents already deliver value in 2026.

07/03/2026 · Industry Trends · 6 min read

Claude Sonnet 5: What's New, How It Benchmarks, and Where Claude Science Fits

Anthropic shipped Claude Sonnet 5, the Claude Science product, and a global-release clearance in one 48-hour window. Here's what actually changed for builders — capabilities and cost first, policy last.

07/02/2026 · Model Evaluation · 8 min read

ZCode vs Claude Code: Z.ai's GLM-5.2 Coding Agent, Compared and Set Up

Z.ai just shipped ZCode, a first-party coding agent built around its open-weight GLM-5.2 model. Here's how it compares to Claude Code, when it fits, and how to get it running.

07/02/2026 · AI Tutorials · 9 min read

OpenClaw Mobile: How to Set It Up on Android and iOS (v2026.6.11 Guide)

OpenClaw is finally on Android and iOS. Here's how to set it up via the OpenClaw Gateway, which messaging channels it supports, and what the v2026.6.11 reliability release fixes.

07/02/2026 · AI Tutorials · 6 min read

Claude Sonnet 5 for Coding Agents: Is the Higher Cost-Per-Task Worth It?

Claude Sonnet 5 keeps Sonnet 4.6's sticker price but a new tokenizer inflates real cost-per-task by roughly 30%. Here's what that means for agentic and coding workloads — and when it's still worth it.

07/02/2026 · Model Evaluation · 7 min read

Can You Trust an AI Model Leaderboard? How LMArena and LLM Benchmarks Really Work

An AI model leaderboard like LMArena is now the industry scoreboard — and a $100M business. Here is how Elo-style ranking actually works, where it misleads, and how to evaluate models for your own use case.

06/30/2026 · Model Evaluation · 8 min read

Prompt Injection Defense: A Builder's Guide to Securing AI Agents

Prompt injection defense is now a shipping requirement for anyone connecting an LLM to tools. Here is what the attack really is, why it can't be patched away, and the defense-in-depth layers to ship before your agent touches anything that matters.

06/30/2026 · AI Tutorials · 8 min read

AI Agents at Work: A Playbook for Deploying Them Without the Hype

AI agents at work are moving from demo to daily driver — Samsung is rolling ChatGPT and Codex to employees, and Notion retired its own email app because users prefer agents. Here's a strategic playbook for where agents pay off and how to deploy them.

06/29/2026 · Industry Trends · 8 min read

How to Evaluate AI Agents: A Practical Reliability Playbook

AI agent evaluation is the discipline most teams skip — and the one that decides whether your agent survives production. Here's how to test agents for correctness, reliability, memory, and failure modes before and after you ship.

06/29/2026 · Model Evaluation · 9 min read

How to Benchmark AI Agents on Your Own Tools (Not Just Leaderboards)

Public leaderboards won't tell you if a model can actually drive your tools. Here's how to build a lightweight, reproducible agentic eval against your own harness — and why local models are now in the running.

06/28/2026 · Model Evaluation · 9 min read

Prompt Injection in 2026: How to Actually Defend Your AI Agents

Prompt injection is still the #1 blocker to shipping AI agents. Here is what the attack really is, why a system prompt won't fix it, and the defense-in-depth patterns that hold up in practice.

06/28/2026 · Research · 9 min read

How to Evaluate AI Agents in 2026: Beyond Benchmark Saturation

Static leaderboards are saturating, so durable agent evaluation is shifting to stress-testing in simulated environments. A practical 2026 framework for measuring whether your AI agent is actually reliable.

06/27/2026 · Model Evaluation · 8 min read

GPT-5.6 "Sol" Explained: What's New, How It Compares to GPT-5, and Why the Rollout Is Restricted

OpenAI previewed GPT-5.6 "Sol" — then limited its rollout after a government request. Here's what's actually confirmed, what isn't yet, and what the restriction signals for frontier-model releases.

06/27/2026 · Industry Trends · 6 min read

The Agent Skills Standard Explained — and How to Write Your First Skill

Agent-skill repos are gaining tens of thousands of stars in weeks as a shared format crystallizes. Here's what the Agent Skills standard actually standardizes — and a grounded, step-by-step walkthrough to writing your first skill.

06/25/2026 · AI Tutorials · 9 min read

How to Secure an AI Agent: Prompt Injection, Role Confusion, and Red-Teaming in 2026

In one week of June 2026, three independent sources reframed agent security — Willison's role-confusion model, the RIFT-Bench red-teaming benchmark, and the MosaicLeaks secret-leak demo. Here's how to secure an AI agent as a trust-boundary problem, not a string-filtering one.

06/25/2026 · Research · 9 min read

Agent Skills Best Practices: How to Structure Them (and the Mistakes to Avoid)

Most agent-skill failures aren't a model problem — they're a structure problem. Here are agent skills best practices: when to write a skill, how to scope and describe it, and how to benchmark whether it actually helps on your own tooling.

06/23/2026 · AI Tutorials · 9 min read

How to Run GLM-5.2 Locally: Setup, Hardware, and How It Stacks Up for Agents

GLM-5.2 is the strongest text-only open-weights LLM right now, and it's built for long-horizon agent work. Here's how to run GLM-5.2 locally, the hardware you actually need, and an honest read on whether it belongs in your agent stack.

06/23/2026 · AI Tutorials · 11 min read

How to Evaluate an AI Agent: Tool-Use Capability and Data-Leakage Risk

A practical framework for evaluating AI agents on two axes that both decide production-readiness: can it do the job on your own tooling, and can it be trusted not to leak data?

06/22/2026 · Model Evaluation · 7 min read

GLM-5.2: The New Leader in Open-Weights LLMs for Long-Horizon Agents

GLM-5.2 ships under an MIT license with a 1M-token context and now tops the open-weights field for long-horizon coding and agent work. Here's the evidence, how it compares, and how to run it.

06/22/2026 · Model Evaluation · 7 min read

Can Your AI Agent Keep a Secret? A 2026 Guide to Agent Data Leakage and Real Evaluation

AI agent security is now an evaluation problem: agents can leak private data through ordinary-looking tool calls and still pass every leaderboard. Here's how data leakage happens, how to red-team it, and how to benchmark whether an agent is actually reliable on your own tools.

06/21/2026 · Model Evaluation · 11 min read

Can Your AI Agent Keep a Secret? Testing Agents for Data Leakage

Capability evals tell you if an agent is smart. They don't tell you whether it will leak the sensitive data it can see. Here's how to test AI agents for data leakage and secret-keeping — grounded in new research and a real-world one-click leak.

06/21/2026 · Model Evaluation · 9 min read

A2A Protocol Explained: How Agents Talk to Other Agents

A live community thread asking "is anyone using A2A?" shows builders are still orienting in the agent-protocol landscape. Here's a vendor-neutral explainer of what the A2A protocol is, the problem it solves, and how it fits alongside MCP — grounded in the official spec.

06/21/2026 · Research · 8 min read

GLM-5.2 for Agents: What's New and How to Run It

GLM-5.2 is being positioned as the most powerful text-only open-weights LLM for long-horizon agents. Here's what changed, how to judge the "most powerful open model" claim, and how to think about running GLM-5.2 in an agent loop.

06/20/2026 · Research · 8 min read

How to Evaluate AI Agents Beyond the Leaderboard

Leaderboard scores don't predict how an AI agent behaves on your real tasks. Here's a practical guide to evaluating LLM agents on your own tools, with the metrics and predictive-validity thinking that actually transfer to production.

06/20/2026 · Model Evaluation · 9 min read

How to Benchmark an LLM's Agentic Tool Use on Your Own Stack

Public leaderboards won't tell you if a model works with your tools. Here's a practical, repeatable methodology to benchmark agentic tool use on your own stack — and the failure modes to watch.

06/20/2026 · AI Tutorials · 9 min read

GLM-5.2 for AI Agents: Benchmarks and How It Compares for Long-Horizon Tasks

GLM-5.2 is a new MIT-licensed, 1M-context open-weights model explicitly tuned for long-horizon agentic work. We break down what's new, the benchmarks that matter for agents, and how to judge it for your own stack.

06/20/2026 · Model Evaluation · 9 min read

Can You Trust an AI Agent? Evaluating Reliability, Data Leakage, and Security

Agent trust isn't a vibe - it's measurable. A practical playbook for evaluating agent reliability, secret-leakage, and security, grounded in this week's benchmarks and a real one-click exploit.

06/20/2026 · Model Evaluation · 9 min read